Origin, structure, and composition of the spider major ampullate silk fiber revealed by genomics, proteomics, and single-cell and spatial transcriptomics

S Sonavane, S Hassan, U Chatterjee, L Soler… - Science …, 2024 - science.org
Spiders produce nature's toughest fiber using renewable components at ambient
temperatures and with water as solvent, making it highly interesting to replicate for the …

Disentangling the Web: An Interdisciplinary Review on the Potential and Feasibility of Spider Silk Bioproduction

G Guessous, L Blake, A Bui, Y Woo… - … Science & Engineering, 2024 - ACS Publications
The remarkable material properties of spider silk, such as its high toughness and tensile
strength combined with its low density, make it a highly sought-after material with myriad …

Engineered Protein Hydrogels as Biomimetic Cellular Scaffolds

Y Liu, AE Gilchrist, SC Heilshorn - Advanced Materials, 2024 - Wiley Online Library
The biochemical and biophysical properties of the extracellular matrix (ECM) play a pivotal
role in regulating cellular behaviors such as proliferation, migration, and differentiation …

Generative retrieval-augmented ontologic graph and multiagent strategies for interpretive large language model-based materials design

MJ Buehler - ACS Engineering Au, 2024 - ACS Publications
Transformer neural networks show promising capabilities, in particular for uses in materials
analysis, design, and manufacturing, including their capacity to work effectively with human …

AtomAgents: Alloy design and discovery through physics-aware multi-modal multi-agent artificial intelligence

A Ghafarollahi, MJ Buehler - arXiv preprint arXiv:2407.10022, 2024 - arxiv.org
The design of alloys is a multi-scale problem that requires a holistic approach that involves
retrieving relevant knowledge, applying advanced computational methods, conducting …

Cephalo: Multi‐Modal Vision‐Language Models for Bio‐Inspired Materials Analysis and Design

MJ Buehler - Advanced Functional Materials, 2024 - Wiley Online Library
Cephalo is presented as a series of multimodal vision large language models (V‐LLMs)
designed for materials science applications, integrating visual and linguistic data for …

Adaptive CVgen: Leveraging reinforcement learning for advanced sampling in protein folding and chemical reactions

W Shen, K Wan, D Li, H Gao, X Shi - … of the National Academy of Sciences, 2024 - pnas.org
Enhanced sampling techniques have traditionally encountered two significant challenges:
identifying suitable reaction coordinates and addressing the exploration–exploitation …

[HTML][HTML] X-LoRA: Mixture of low-rank adapter experts, a flexible framework for large language models with applications in protein mechanics and molecular design

EL Buehler, MJ Buehler - APL Machine Learning, 2024 - pubs.aip.org
We report a mixture of expert strategy to create fine-tuned large language models using a
deep layer-wise token-level approach based on low-rank adaptation (LoRA). Starting with a …

ProtAgents: protein discovery via large language model multi-agent collaborations combining physics and machine learning

A Ghafarollahi, MJ Buehler - Digital Discovery, 2024 - pubs.rsc.org
Designing de novo proteins beyond those found in nature holds significant promise for
advancements in both scientific and engineering applications. Current methodologies for …

Artificial Spider Silk Materials: From Molecular Design, Mesoscopic Assembly, to Macroscopic Performances

YX Shi, YJ Zhu, ZG Qian, XX Xia - Advanced Functional …, 2024 - Wiley Online Library
Spider silk is one of the strongest and toughest fibrous materials available in nature. Its
superior properties make it a good candidate for applications in various fields ranging from …